Completions

Create completion

Changed on

Creates a completion for the provided prompt and parameters.

Returns a completion object, or a sequence of completion objects if the request is streamed.

post/completions

Request

  • Base URL
    https://api.openai.com/v1
  • URL
    https://api.openai.com/v1/completions
  • Auth
    HTTP bearer

Request body

best_ofinteger nullable

Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.

When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

echoboolean nullable

Echo back the prompt in addition to the completion

frequency_penaltynumber nullable

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

See more information about frequency and presence penalties.

logit_biasobject nullable

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.

logprobsinteger nullable

Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.

The maximum value for logprobs is 5.

max_tokensinteger nullable

The maximum number of tokens that can be generated in the completion.

The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

ninteger nullable

How many completions to generate for each prompt.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

presence_penaltynumber nullable

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

See more information about frequency and presence penalties.

seedinteger nullable

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

streamboolean nullable

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

suffixstring nullable

The suffix that comes after a completion of inserted text.

This parameter is only supported for gpt-3.5-turbo-instruct.

temperaturenumber nullable

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

top_pnumber nullable

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

userstring

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example request

{
  "prompt": "This is a test.",
  "max_tokens": 16,
  "n": 1,
  "stop": "\n",
  "suffix": "test.",
  "temperature": 1,
  "top_p": 1,
  "user": "user-1234"
}

Response

OK

idstring required

A unique identifier for the completion.

createdinteger required

The Unix timestamp (in seconds) of when the completion was created.

modelstring required

The model used for completion.

system_fingerprintstring

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

object'text_completion' required

The object type, which is always "text_completion"

Changes

  • c8669635a97dRevision changes
    • info

      added the media type text/event-stream for the response with the status

  • e2f8d8cbc41fRevision changes
    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status